mirror of
https://github.com/block/buzz.git
synced 2026-08-18 06:50:31 +02:00
npub1mn7jgtj4w2pd0g0zeuhxsa6jy6p0rewxz4kujt98my82ahfmp72sxjexk7andWill Pfleger
144ef4d9d0
The frontend heuristic in #3586 title-cased every word and converted adjacent digit pairs to decimals for any string starting with 'databricks-'. This invented false labels for custom workspace endpoints: 'databricks-team-2025-01' → 'Team 2025.01', 'databricks-finance-2025-01-30' → 'Finance 2025.01 30'. Replace with a lookup-and-pass-through approach drawn from the same design goose uses in production: - Generator script (scripts/generate-databricks-model-names.py) fetches https://models.dev/api.json and emits a sorted Rust static slice of (id, name) pairs under crates/buzz-agent/src/databricks_model_names.rs. Refresh by rerunning the script and committing the diff. - catalog.rs consults the table via databricks_model_name(id): known managed endpoints get curated names (e.g. 'databricks-gpt-5-5' → 'GPT-5.5'), unknown/custom endpoints return their raw ID unchanged. Applied to all ModelEntry construction paths: v1/v2 discovery, the empty-list fallback, and discovery_failure_fallback. - Frontend: a matching TS registry (desktop/src/features/agents/lib/ databricksModelNames.ts) covers persisted raw IDs on cards, rows, and popovers that render before discovery data is available. formatAgentModelLabel and formatDefaultModelLabel use the registry; no heuristic string mangling exists anywhere in the TS layer. - AGENTS.md documents the three-tier label precedence: API/runtime name first, table-backed fallback second, raw ID last. Supersedes #3586 (kennylopez-model-display-labels). Co-authored-by: Will Pfleger <pfleger.will@gmail.com> Signed-off-by: Will Pfleger <pfleger.will@gmail.com>
73 lines
2.3 KiB
Python
Executable File
73 lines
2.3 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Generate crates/buzz-agent/src/databricks_model_names.rs from models.dev.
|
|
|
|
Usage:
|
|
python3 scripts/generate-databricks-model-names.py \
|
|
> crates/buzz-agent/src/databricks_model_names.rs
|
|
|
|
Fetches https://models.dev/api.json, extracts providers.databricks.models (the
|
|
authoritative curated name registry used by goose and others), and emits a
|
|
static Rust slice of (id, display_name) pairs sorted by ID.
|
|
|
|
Re-run whenever Databricks ships a new managed endpoint and commit the diff.
|
|
"""
|
|
|
|
import json
|
|
import subprocess
|
|
import sys
|
|
|
|
|
|
URL = "https://models.dev/api.json"
|
|
|
|
|
|
def fetch(url: str) -> bytes:
|
|
# urllib blocks with HTTP 403 without a browser User-Agent; use curl when
|
|
# available so the script works in hermit environments where curl is pinned.
|
|
result = subprocess.run(
|
|
["curl", "-s", "-A", "Mozilla/5.0", url],
|
|
capture_output=True,
|
|
check=True,
|
|
)
|
|
return result.stdout
|
|
|
|
|
|
def rust_str(s: str) -> str:
|
|
"""Emit a Rust string literal with double quotes."""
|
|
escaped = s.replace("\\", "\\\\").replace('"', '\\"')
|
|
return f'"{escaped}"'
|
|
|
|
|
|
def main() -> None:
|
|
raw = fetch(URL)
|
|
data = json.loads(raw)
|
|
models: dict = data["databricks"]["models"]
|
|
entries = sorted(
|
|
(k, v["name"] if isinstance(v, dict) else k) for k, v in models.items()
|
|
)
|
|
|
|
lines = [
|
|
"// GENERATED by scripts/generate-databricks-model-names.py",
|
|
"// Source: https://models.dev/api.json -- providers.databricks.models",
|
|
"// Refresh: python3 scripts/generate-databricks-model-names.py \\",
|
|
"// > crates/buzz-agent/src/databricks_model_names.rs",
|
|
"//",
|
|
"// Do not hand-edit -- rerun the script to update.",
|
|
"",
|
|
"/// Curated display names for known Databricks AI Gateway endpoints.",
|
|
"///",
|
|
"/// Keys are endpoint IDs returned verbatim by the discovery APIs.",
|
|
"/// Values are human-readable display names sourced from models.dev.",
|
|
"///",
|
|
"/// Unknown endpoint IDs are displayed as their raw ID -- no guessing.",
|
|
"pub(crate) static DATABRICKS_MODEL_NAMES: &[(&str, &str)] = &[",
|
|
]
|
|
for id_, name in entries:
|
|
lines.append(f" ({rust_str(id_)}, {rust_str(name)}),")
|
|
lines += ["];", ""]
|
|
|
|
sys.stdout.write("\n".join(lines))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|